Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    abbreviations for various organizations or authorities

    oai_token-act-pair · gpt-3.5-turbo

    acronyms and abbreviations of organizations or authorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     weap
    -0.74
     unden
    -0.74
     captcha
    -0.65
     tremend
    -0.64
     piston
    -0.63
     showc
    -0.63
     neigh
    -0.62
     charact
    -0.61
     caution
    -0.61
    catentry
    -0.61
    POSITIVE LOGITS
    )
    1.31
    ),
    1.30
    )—
    1.17
    )'
    1.16
    ).
    1.09
    )[
    1.06
    )),
    1.00
    ),"
    0.99
    )...
    0.97
    )-
    0.96
    Act Density 0.082%

    No Known Activations